Downloads · 30 days
8
3% of all-time downloads
shisa-ai/ablation-195-finalsft2-shisa-v2-mistral-small-24b
ablation-195-finalsft2-shisa-v2-mistral-small-24b is a text generation model from shisa-ai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
8
3% of all-time downloads
All-time downloads
311
Public
Parameters
23.6B
47.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors47.1 GB · 100%
From the Hugging Face model README
axolotl version: 0.8.0.dev0
# train w/ shisa-ai/shisa-v1-athenev2-reannotated-filtered
base_model: mistralai/Mistral-Small-24B-Instruct-2501
load_in_8bit: false
load_in_4bit: false
strict: false
# User Liger
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true
chat_template: mistral_v7_tekken
datasets:
- path: shisa-ai/shisa-v2-best-of-n-athenev2-tulu70b-llama33-only-no-sysprompt
type: chat_template
field_messages: conversations
message_field_role: from
message_field_content: value
- path: shisa-ai/shisa-v2-roleplaying-sft
type: chat_template
field_messages: conversations
message_property_mappings:
role: role
content: content
roles:
system:
- system
assistant:
- gpt
- model
- assistant
user:
- human
- user
roles_to_train: ["assistant"]
- path: shisa-ai/translation_set_april_6
split: train[:25%]
type: chat_template
field_messages: conversations
message_property_mappings:
role: role
content: content
roles:
system:
- system
assistant:
- gpt
- model
- assistant
user:
- human
- user
roles_to_train: ["assistant"]
- path: shisa-ai/rewild-set-deepseek-subset
split: train[:25%]
type: chat_template
field_messages: conversations
message_property_mappings:
role: role
content: content
roles:
system:
- system
assistant:
- gpt
- model
- assistant
user:
- human
- user
roles_to_train: ["assistant"]
- path: shisa-ai/magpie-ultra-set
split: train[:8%]
type: chat_template
field_messages: conversations
message_property_mappings:
role: role
content: content
roles:
system:
- system
assistant:
- gpt
- model
- assistant
user:
- human
- user
roles_to_train: ["assistant"]
- path: shisa-ai/magpie-advanced-questions-set
split: train[:8%]
type: chat_template
field_messages: conversations
message_property_mappings:
role: role
content: content
roles:
system:
- system
assistant:
- gpt
- model
- assistant
user:
- human
- user
roles_to_train: ["assistant"]
- path: shisa-ai/japan-magpie-set
split: train
type: chat_template
field_messages: conversations
message_property_mappings:
role: role
content: content
roles:
system:
- system
assistant:
- gpt
- model
- assistant
user:
- human
- user
roles_to_train: ["assistant"]
- path: shisa-ai/shisa-v2-instruction-following-sft
split: train[:50%]
type: chat_template
field_messages: conversations
message_property_mappings:
role: role
content: content
roles:
system:
- system
assistant:
- gpt
- model
- assistant
user:
- human
- user
roles_to_train: ["assistant"]
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/ablation-195-finalsft2-shisa-v2-mistral-small-24b
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
# marginal difference
neftune_noise_alpha: 5
use_wandb: true
wandb_project: shisa-v2
wandb_entity: augmxnt
wandb_name: ablation-195-finalsft2-shisa-v2-mistral-small-24b
gradient_accumulation_steps: 1
micro_batch_size: 4
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: linear
learning_rate: 5.8e-6
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 100
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 0
save_total_limit: 1 # Only store a single checkpoint
debug:
deepspeed: zero3_bf16.json
weight_decay: 1e-4
fsdp:
fsdp_config:
special_tokens:
</details><br>
This model is a fine-tuned version of mistralai/Mistral-Small-24B-Instruct-2501 on the shisa-ai/shisa-v2-best-of-n-athenev2-tulu70b-llama33-only-no-sysprompt, the shisa-ai/shisa-v2-roleplaying-sft, the shisa-ai/translation_set_april_6, the shisa-ai/rewild-set-deepseek-subset, the shisa-ai/magpie-ultra-set, the shisa-ai/magpie-advanced-questions-set, the shisa-ai/japan-magpie-set and the shisa-ai/shisa-v2-instruction-following-sft datasets. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8376 | 0.0022 | 1 | 0.8441 |
| 0.5706 | 0.5011 | 229 | 0.5798 |
| 0.4254 | 1.0022 | 458 | 0.5555 |
| 0.4167 | 1.5033 | 687 | 0.5570 |
| 0.302 | 2.0044 | 916 | 0.5593 |
| 0.3056 | 2.5055 | 1145 | 0.5855 |